Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Hotfix/optimizing updates #42

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Hotfix/optimizing updates #42

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c6638a0
Ignore models
margon8 May 20, 2024
542c559
Separate the append ops when its optimizing and when its not
margon8 May 22, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@
#Input of tests
src/test/resources/prod/*
src/test/scala/EndToEndTest.scala
src/test/models/*

#Output of tests
src/test/tmp/*
Expand Down
38 changes: 27 additions & 11 deletions src/main/scala/com/metabolic/data/core/services/spark/writer/file/DeltaWriter.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@ class DeltaWriter(val outputPath: String, val writeMode: WriteMode,
.option("txnVersion", batchId).option("txnAppId", output_identifier)
.delta(output_identifier)

if (optimize && batchId % optimizeEvery == 0) {
if (batchId % optimizeEvery == 0) {
compactAndVacuum
}

Expand Down Expand Up @@ -142,25 +142,41 @@ class DeltaWriter(val outputPath: String, val writeMode: WriteMode,
override def writeStream(df: DataFrame): StreamingQuery = {

val data_query = writeMode match {
case WriteMode.Append => df
.writeStream
.outputMode("append")
.option("mergeSchema", "true")
.option("checkpointLocation", checkpointLocation)
.foreachBatch(appendToDelta _)
.start
case WriteMode.Append =>

val sw = df
.writeStream
.outputMode("append")
.option("mergeSchema", "true")
.option("checkpointLocation", checkpointLocation)

if (optimize) {
sw
.foreachBatch(appendToDelta _)
.start
} else {
sw
.delta(output_identifier)
}

case WriteMode.Overwrite =>

DeltaTable.forPath(outputPath).delete()

df
val sw = df
.writeStream
.outputMode("append")
.option("overwriteSchema", "true")
.option("checkpointLocation", checkpointLocation)
.foreachBatch(appendToDelta _)
.start

if (optimize) {
sw
.foreachBatch(appendToDelta _)
.start
} else {
sw
.delta(output_identifier)
}

case WriteMode.Upsert => df
.writeStream
Expand Down
Loading